Use of machine learning and Poincaré density grid in the diagnosis of sinus node dysfunction caused by sinoatrial conduction block in dogs.

BACKGROUND: Sinus node dysfunction because of abnormal impulse generation or sinoatrial conduction block causes bradycardia that can be difficult to differentiate from high parasympathetic/low sympathetic modulation (HP/LSM). HYPOTHESIS: Beat-to-beat relationships of sinus node dysfunction are quantifiably distinguishable by Poincaré plots, machine learning, and 3-dimensional density grid analysis. Moreover, computer modeling establishes sinoatrial conduction block as a mechanism. ANIMALS: Three groups of dogs were studied with a diagnosis of: (1) balanced autonomic modulation (n = 26), (2) HP/LSM (n = 26), and (3) sinus node dysfunction (n = 21). METHODS: Heart rate parameters and Poincaré plot data were determined [median (25%-75%)]. Recordings were randomly assigned to training or testing. Supervised machine learning of the training data was evaluated with the testing data. The computer model included impulse rate, exit block probability, and HP/LSM. RESULTS: Confusion matrices illustrated the effectiveness in diagnosing by both machine learning and Poincaré density grid. Sinus pauses >2 s differentiated (P < .0001) HP/LSM (2340; 583-3947 s) from sinus node dysfunction (8503; 7078-10 050 s), but average heart rate did not. The shortest linear intervals were longer with sinus node dysfunction (315; 278-323 ms) vs HP/LSM (260; 251-292 ms; P = .008), but the longest linear intervals were shorter with sinus node dysfunction (620; 565-698 ms) vs HP/LSM (843; 799-888 ms; P < .0001). CONCLUSIONS: Number and duration of pauses, not heart rate, differentiated sinus node dysfunction from HP/LSM. Machine learning and Poincaré density grid can accurately identify sinus node dysfunction. Computer modeling supports sinoatrial conduction block as a mechanism of sinus node dysfunction.

The Anatomical Substrate for Sick Sinus Syndrome in Dogs.

The hearts of 28 dogs, clinically diagnosed as having symptomatic sick sinus syndrome (SSS), were examined post mortem, with a particular focus on the sinus node (SN) region. The affected dogs were divided into two groups according to the findings of ambulatory electrocardiography: 16 dogs with severe sinoatrial (SA) block and/or sinus arrest (group A) and 12 dogs with long sinus or atrial pauses due to SA block and/or sinus arrest accompanied by atrial tachyarrhythmias (group B). The most significant histopathological changes found in both SSS groups were extensive destruction of the SN characterized by depletion of nodal cells with fatty or fibrofatty replacement and interruption of contiguity between the SN and the surrounding atrial myocardium. Furthermore, in group B, the SN lesions were combined with fibrosis of the atrial myocardium. The results of this investigation improve our understanding of the close relationship between the electrocardiogram findings and pathological alterations in each group. Because most human cases of SSS are due to degenerative fibrosis of the SN, the loss and disappearance of nodal cells with a corresponding increase in fatty or fibrofatty tissue, may be specific to canine cases of SSS.

[Electrocardiography in the horse. (2). Disorders of impulse formation and impulse conduction]. / Elektrokardiographie beim Pferd. (2). Erregungsbildungs-und Erregungsleitungsstörungen.

The cardiac arrhythmias, classified in disturbances of impulse formation and conduction disturbances, their genesis and clinical significance are described and illustrated with electrocardiograms, registered with the bipolar chest leads.

Electrocardiography in the horse. (A report of findings in 138 horses).

Over a period of approx. 3 years, electrocardiograms (ECG) were recorded from 138 horses referred as patients to the Medical Clinic. Of these, 22 horses (approx. 16 per cent) has ECG alterations. The 22 ECG's revealed a total of 29 ECG abnormalities. The most frequent ECG alteration was incomplete AV block, that was seen in 9 horses (31 per cent of the ECG abnormalities). Abnormal (i.e. broad, tent-like and, sometimes, inverted) T waves and deviations of the ST segment were seen each in 5 ECG's from 7 horses, 3 of which had both abnormalities which were associated with severe underlying disease (colic, enteritis, pneumonia, strangles a.o.). Premature ventricular beats were seen in 3 horses, two of which had serious cardiovascular dysfunction whereas the third showed no signs of cardiac disease. Atrial fibrillation was observed in two horses. Both were treated with chinidine sulphate but a conversion to sinus rhythm was not achieved in either case. Other ECG abnormalities observed in the study were, parasystole (1 horse), sinus arrhythmia (2 horses), sinoatrial block (1 horse) and wandering pacemaker (1 horse). Each abnormality is discussed with regard to its clinical significance and diagnosis. Cardiac murmurs were detected on auscultation of 26 horses (approx. 19 per cent). The murmurs in 15 horses were short and faint sounds most of which were diastolic. They were considered of no importance. Eleven horses, on the other hand, had distinct, loud (grade 4 or 5), holosystolic or holodiastolic murmurs that were considered pathological. Eight of these horses had actual signs of cardiac disease. Cardiac vector distribution in patients with ECG abnormalities or murmurs showed no systematic differences from vectors in horses showing no cardiac abnormality.